When performing inservice inspection on a large volume of identical co
mponents, it becomes an almost impossible task to inspect all those in
which defects may exist, even if their failure probabilities are know
n. As a result, an appropriate sample size needs to be determined when
setting rtp an inspection program. In this paper, a probabilistic ana
lysis method is employed to solve this problem. It is assumed that the
characteristic data of components has a certain distribution which ca
n be taken as known when the mean and standard deviations of serviceab
le and defective sets of components are estimated. The sample size can
then be determined within an acceptable assigned error range. In this
way, both false rejection and acceptance can be avoided with a high d
egree of confidence.